agentleFS
timscheueraitimscheuerai/gtm-architecture-template/.agents/skills/signals-sweep/SKILL.md

signals-sweep

Skill2 starsChanged 2 months agoMITView on GitHub

Collect a bounded batch of hiring, engagement or other account signals with source dates, deduplication and explicit qualification rules.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the active ICP, exclusions and runtime contract.

    line 8
  2. Very specific:

    Keep stable event ID, company identity, source URL, event type, occurred/observed/indexed dates where available, query term and collection …

    line 12
  3. Distinctive:

    Run independent fit checks before contact enrichment.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Collect useful signals

Read the active ICP, exclusions and runtime contract. Define the business event, why it could matter, date window, source, buyer hypothesis and maximum batch size.

Inspect the provider's current filter semantics: HQ geography differs from job or person geography; event time differs from indexing time. Use the timestamp the hypothesis actually needs. Unknown dates remain unknown rather than becoming fresh.

Keep stable event ID, company identity, source URL, event type, occurred/observed/indexed dates where available, query term and collection batch. Convert a known timestamp to Unix milliseconds only at the function boundary. Do not silently invent the missing event date.

Preview scope and current cost; count-only calls can also be billable. Follow pagination and persist resumable state in OXYGEN. Deduplicate on provider/event ID and preserve multiple genuine signals per company.

Run independent fit checks before contact enrichment. Exclusions come from the current company brief; substring matches are review hints, not definitive identity matches. Use prioritise_accounts and prioritise_contacts with an explicit evaluation time and signal lifetime.

Report fresh/duplicate/unknown/held counts and incomplete pages. Engagement does not establish buyer intent. For comment-to-resource requests, deliver only the requested resource through the authorized channel; use oxygen-sequencer-enroll for a separately authorized outreach motion.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.